Execute and manage multi-step workflows with progress tracking, error handling, and validation. Use when running complex development workflows, coordinating multi-phase tasks, or managing workflow state and recovery.
Execute and manage multi-step workflows with progress tracking, error handling, and validation. Use when running complex development workflows, coordinating multi-phase tasks, or managing workflow state and recovery.
/plugin marketplace add L-Sypniewski/claude-code-toolkit/plugin install development-workflow@claude-code-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
guides/error-handling.mdguides/progress-tracking.mdguides/workflow-templates.mdExecute and manage complex workflows with multiple phases and validation points.
Break workflows into distinct phases with clear boundaries:
Phase 1: Analysis β Phase 2: Implementation β Phase 3: Validation
Each phase should have:
Track progress explicitly so status is always clear:
### Phase 2: Implementation π
- [x] Core functionality
- [ ] Edge cases
- [ ] Tests
Symbols: β Complete | π In Progress | βΈοΈ Blocked | β Failed
Every workflow should handle failures:
Step 1 β Step 2 β Step 3 β Done
Use when: Each step depends on the previous step's output
ββ Task A β
Startββ Task B ββ Merge β Continue
ββ Task C β
Use when: Tasks are independent and can run concurrently
Plan β Execute β Review β [Refine] β Loop until done
Use when: Requirements evolve or refinement cycles needed
For detailed tracking patterns, see guides/progress-tracking.md.
Quick reference - Status template:
## Workflow Status
### Phase 1: [Name] β
- [x] Task completed
### Phase 2: [Name] π
- [x] Task done
- [ ] Task pending
For error handling strategies, see guides/error-handling.md.
Quick reference - When failures occur:
For ready-to-use templates, see guides/workflow-templates.md.
Available templates:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.